In [48]:
# Confusion matrix in sklearn
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
# Actual values
actual = y_test
# Predicted values
predicted = y_pred
# Confusion matrix
matrix = confusion_matrix(actual,predicted, labels=[1,0], sample_weight=None, normalize=None)
print('Confusion matrix : \n', matrix)
# Outcome values order in sklearn
tp, fn, fp, tn = confusion_matrix(actual,predicted,labels=[1,0]).reshape(-1)
print('Outcome values : \n', tp, fn, fp, tn)
# Classification report for precision, recall f1-score and accuracy
C_Report = classification_report(actual,predicted,labels=[1,0])
print('Classification report : \n', C_Report)
# Calculating the metrics
sensitivity = round(tp/(tp+fn), 3);
specificity = round(tn/(tn+fp), 3);
accuracy = round((tp+tn)/(tp+fp+tn+fn), 3);
balanced_accuracy = round((sensitivity+specificity)/2, 3);
precision = round(tp/(tp+fp), 3);
f1Score = round((2*tp/(2*tp + fp + fn)), 3);
# Matthews Correlation Coefficient (MCC). Range of values of MCC lie between -1 to +1.
# A model with a score of +1 is a perfect model and -1 is a poor model
from math import sqrt
mx = (tp+fp) * (tp+fn) * (tn+fp) * (tn+fn)
MCC = round(((tp * tn) - (fp * fn)) / sqrt(mx), 3)
print('Accuracy :', round(accuracy*100, 2),'%')
print('Precision :', round(precision*100, 2),'%')
print('Recall :', round(sensitivity*100,2), '%')
print('F1 Score :', f1Score)
print('Specificity or True Negative Rate :', round(specificity*100,2), '%')
print('Balanced Accuracy :', round(balanced_accuracy*100, 2),'%')
print('MCC :', MCC)
# Area under ROC curve
from sklearn.metrics import roc_curve, roc_auc_score
print('roc_auc_score:', round(roc_auc_score(actual, predicted), 3))
# ROC Curve
from sklearn.metrics import roc_auc_score
from sklearn.metrics import roc_curve
model_roc_auc = roc_auc_score(actual, predicted)
fpr, tpr, thresholds = roc_curve(actual, ModelLR.predict_proba(x_test)[:,1])
plt.figure()
#----------------------------------------------------
plt.plot(fpr, tpr, label= 'Classification Model' % model_roc_auc)
plt.plot([0, 1], [0, 1],'r--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic')
plt.legend(loc="lower right")
plt.show()
print('-----------------------------------------------------------------------------------------------------')
Confusion matrix :
[[ 0 262]
[ 0 7376]]
Outcome values :
0 262 0 7376
Classification report :
precision recall f1-score support
1 0.00 0.00 0.00 262
0 0.97 1.00 0.98 7376
accuracy 0.97 7638
macro avg 0.48 0.50 0.49 7638
weighted avg 0.93 0.97 0.95 7638
Accuracy : 96.6 %
Precision : nan %
Recall : 0.0 %
F1 Score : 0.0
Specificity or True Negative Rate : 100.0 %
Balanced Accuracy : 50.0 %
MCC : nan
roc_auc_score: 0.5
-----------------------------------------------------------------------------------------------------
